diff_of_means ratio_of_sd amplitude_ratio_of_means maximum_error ks_mean_on_coarse_res_with_extremes qqplot_mae acf_mae extremogram_mae rainy_hours_ratio_of_means
xgboost.cesm2.ssp370 0.39% 0.891 0.549 0.364 0.394 0.023 0.123 0.096 0.839
nv.cesm2.ssp245 -1.10% 0.830 0.539 0.302 0.587 0.029 0.152 0.109 0.815
xgboost.cesm2.ssp585 1.34% 0.907 0.553 0.375 0.429 0.020 0.118 0.103 0.861
lstm.mri_esm2_0.ssp434 -2.38% 0.902 0.601 0.305 0.288 0.026 0.103 0.084 0.908
cnn.mri_esm2_0.ssp434 -2.99% 0.849 0.634 0.330 0.215 0.038 0.081 0.062 0.953
lstm.mri_esm2_0.ssp245 -3.18% 0.899 0.600 0.286 0.333 0.025 0.117 0.094 0.926
lstm.cesm2.ssp585 -3.44% 0.920 0.609 0.308 0.302 0.025 0.101 0.074 0.849
xgboost.cesm2.ssp245 3.52% 0.862 0.553 0.356 0.447 0.022 0.115 0.092 0.874
lstm.cesm2.ssp370 -3.85% 0.901 0.609 0.314 0.240 0.027 0.102 0.070 0.819
nv.cesm2.ssp585 -4.32% 0.901 0.551 0.315 0.474 0.026 0.154 0.124 0.808
nv.cesm2.ssp370 -4.78% 0.894 0.552 0.316 0.378 0.028 0.147 0.117 0.792
cnn.mri_esm2_0.ssp245 -4.99% 0.851 0.636 0.336 0.294 0.035 0.104 0.090 0.953
lstm.cesm2.ssp245 -5.15% 0.933 0.645 0.308 0.316 0.018 0.096 0.056 0.861
cnn.cesm2.ssp585 -5.84% 0.866 0.657 0.322 0.196 0.037 0.082 0.063 0.875
nv.mri_esm2_0.ssp370 6.06% 0.787 0.511 0.275 0.565 0.029 0.154 0.106 0.874
lstm.mri_esm2_0.ssp370 -6.79% 0.941 0.648 0.299 0.322 0.017 0.097 0.048 0.888
cnn.cesm2.ssp370 -6.86% 0.848 0.653 0.319 0.186 0.040 0.086 0.063 0.852
cnn.mri_esm2_0.ssp370 -8.56% 0.891 0.676 0.316 0.267 0.028 0.086 0.056 0.927
cnn.cesm2.ssp245 -8.94% 0.877 0.685 0.319 0.263 0.032 0.085 0.060 0.872
lstm.ec_earth3.ssp434 -10.22% 0.943 0.685 0.335 0.244 0.023 0.114 0.048 0.809
cnn.ec_earth3.ssp434 -10.33% 0.875 0.717 0.315 0.176 0.034 0.099 0.045 0.821
xgboost.mri_esm2_0.ssp370 12.85% 0.795 0.513 0.362 0.476 0.025 0.107 0.089 0.968
nv.mri_esm2_0.ssp434 18.19% 0.734 0.465 0.276 0.473 0.036 0.153 0.135 0.979
nv.mri_esm2_0.ssp245 19.99% 0.709 0.451 0.281 0.569 0.037 0.171 0.161 0.995
xgboost.ec_earth3.ssp434 -22.40% 0.943 0.625 0.371 0.349 0.041 0.150 0.088 0.694
xgboost.mri_esm2_0.ssp434 23.77% 0.739 0.459 0.370 0.425 0.037 0.109 0.120 1.076
nv.ec_earth3.ssp434 -24.89% 0.884 0.599 0.295 0.442 0.053 0.182 0.103 0.655
xgboost.mri_esm2_0.ssp245 25.34% 0.708 0.445 0.371 0.478 0.039 0.129 0.136 1.074

Time series of the first days

How Often Peaks Hit Hourly

QQ Plot

Distribution of the undownscaled value on days with estimated extremes values.

On the x-axis we have the daily mean (standardized). It says Undownscaled value, but is the daily mean after the downscaling. A good idea is to plot the original undownscaled value.

The purpose of this plot is to illustrate the distribution of P(undownscaled value | we predicted an extreme). This is useful because it reveals how much information we can recover concerning extreme events. If the distribution is skewed to the right, it suggests that we’re predicting extreme values only when extreme values have already occurred. Conversely, if the lower tail of the distribution resembles the reanalysis data, it indicates that we can capture short-duration extremes (e.g., brief periods of heavy rainfall, such as an intense downpour lasting an hour before stopping).

Autocorrelogram

Extremogram